© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27367
    Prev
    Next
    INDEX
    Explanations

    units of distance and area

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ion
    -0.07
    lö
    -0.06
    è¡ĮåĬ¨ä¸Ń
    -0.06
    inho
    -0.06
    åĵ½
    -0.06
    nom
    -0.06
    ner
    -0.06
    но
    -0.06
    an
    -0.06
    иÑĢа
    -0.06
    POSITIVE LOGITS
    ç«ĭæĸ¹
    0.09
    0.08
    <|box_end|>
    0.08
    .gov
    0.08
    æŃ£æĸ¹å½¢
    0.08
    å¹³æĸ¹
    0.08
    ä¸ĩå¥Ĺ
    0.08
     Aires
    0.08
    _sq
    0.08
    Saga
    0.08
    Activations Density 0.017%

    No Known Activations